Revert PDF generation; simplify to DOCX + MD + JSON only

- Remove PDF helpers, LibreOffice, PyPDF2, reportlab
- Transcript DOCX: standalone, no cover page, with line numbering
- Summary DOCX: standalone, no cover page, no line numbering
- Attachments:
  - Transcribe: JSON, transcript MD, transcript DOCX
  - Transcribe & Summarize: JSON, transcript MD, transcript DOCX, summary MD, summary DOCX

scraibe/tasks.py

@@ -14,7 +14,6 @@ from .summarizer import SummarizerClient, SummarizerError
 from .misc import setup_logging
 from .email_sender import send_email, EmailError, load_template
 from .email_sender import create_transcript_docx, create_summary_docx
-from .email_sender import create_combined_docx, generate_pdf_documents
 
 logger = logging.getLogger("scraibe.tasks")
 
@@ -93,7 +92,7 @@ def get_queue_position(task_id: str) -> int:
             if found:
                 break
 
-        # If not found in reserved, it may already be active or not yet visible. 
+        # If not found in reserved, it may already be active or not yet visible.
         # In that case, treat it as position 1.
         if found:
             return max(ahead + 1, 1)
@@ -415,59 +414,6 @@ def process_transcription_task(
                 )
                 speaker_map = {}
 
-        # 3c) Generate short cover-page descriptions using summarizer
-        transcript_cover_desc = ""
-        summary_cover_desc = ""
-        dt = datetime.utcnow()
-        today_str = f"{dt.strftime('%B')} {dt.day}, {dt.year}"
-
-        try:
-            scraibe._ensure_summarizer()
-            summarizer = scraibe._summarizer
-
-            # Transcript description
-            prompt = (
-                "In one short sentence (max 25 words), describe the content of this transcript "
-                "for use on a cover page. Do not include speaker names. Output only the sentence.\n\n"
-                + transcript_text
-            )
-            response = summarizer._chat_completion(
-                messages=[{"role": "user", "content": prompt}],
-                temperature=0.3,
-                max_tokens=60,
-            )
-            transcript_cover_desc = (
-                (response or {}).get("choices", [{}])[0].get("message", {}).get("content", "")
-            ).strip()
-            if not transcript_cover_desc:
-                transcript_cover_desc = "Transcript of the recorded conversation."
-            logger.info("Transcript cover description: %s", transcript_cover_desc)
-
-            # Summary description (if summary requested)
-            if include_summary:
-                prompt = (
-                    "In one short sentence (max 25 words), describe the content of this summary "
-                    "for use on a cover page. Output only the sentence.\n\n"
-                    + summary_text
-                )
-                response = summarizer._chat_completion(
-                    messages=[{"role": "user", "content": prompt}],
-                    temperature=0.3,
-                    max_tokens=60,
-                )
-                summary_cover_desc = (
-                    (response or {}).get("choices", [{}])[0].get("message", {}).get("content", "")
-                ).strip()
-                if not summary_cover_desc:
-                    summary_cover_desc = "Summary of the recorded conversation."
-                logger.info("Summary cover description: %s", summary_cover_desc)
-
-        except (SummarizerError, Exception) as e:
-            logger.warning("Failed to generate cover descriptions: %s", e)
-            transcript_cover_desc = transcript_cover_desc or "Transcript of the recorded conversation."
-            if include_summary:
-                summary_cover_desc = summary_cover_desc or "Summary of the recorded conversation."
-
         # 4) Prepare files
 
         # Transcript .md
@@ -477,14 +423,11 @@ def process_transcription_task(
             f.write(transcript_text)
         temp_files.append(md_transcript_path)
 
-        # Transcript .docx (standalone, with cover page)
+        # Transcript .docx (standalone, no cover page)
         docx_transcript_path = _safe_filename("TRANSCRIPT", local, date_tag, ".docx")
         create_transcript_docx(
             transcript_text,
             docx_transcript_path,
-            include_cover=True,
-            cover_date=today_str,
-            cover_desc=transcript_cover_desc,
         )
         temp_files.append(docx_transcript_path)
 
@@ -511,7 +454,6 @@ def process_transcription_task(
         # Summary files (if present)
         md_summary_path = None
         docx_summary_path = None
-        docx_combined_path = None
 
         if summary_text:
             # Summary .md
@@ -521,77 +463,26 @@ def process_transcription_task(
                 f.write(summary_text)
             temp_files.append(md_summary_path)
 
-            # Summary .docx (standalone, with cover page)
+            # Summary .docx (standalone, no cover page)
             docx_summary_path = _safe_filename("SUMMARY", local, date_tag, ".docx")
             create_summary_docx(
                 summary_text,
                 docx_summary_path,
-                include_cover=True,
-                cover_date=today_str,
-                cover_desc=summary_cover_desc,
             )
             temp_files.append(docx_summary_path)
 
-            # Combined .docx: Transcript + Summary with cover pages
-            docx_combined_path = _safe_filename("TRANSCRIPT_AND_SUMMARY", local, date_tag, ".docx")
-            create_combined_docx(
-                transcript_text=transcript_text,
-                summary_text=summary_text,
-                filename=docx_combined_path,
-                transcript_cover_date=today_str,
-                transcript_cover_desc=transcript_cover_desc,
-                summary_cover_date=today_str,
-                summary_cover_desc=summary_cover_desc,
-            )
-            temp_files.append(docx_combined_path)
-
-        # 4b) Generate PDF documents
-
-        # Always use transcript text; use summary_text only if include_summary is True
-        pdf_summary_text = summary_text if include_summary else ""
-
-        pdf_files = {}
-        try:
-            pdf_output_dir = tempfile.mkdtemp(prefix="pdf_output_")
-            pdf_files = generate_pdf_documents(
-                transcript_text=transcript_text,
-                summary_text=pdf_summary_text,
-                output_dir=pdf_output_dir,
-                transcript_cover_date=today_str,
-                transcript_cover_desc=transcript_cover_desc,
-                summary_cover_date=today_str,
-                summary_cover_desc=summary_cover_desc,
-            )
-            for pdf_path in pdf_files.values():
-                if pdf_path and os.path.exists(pdf_path):
-                    temp_files.append(pdf_path)
-        except Exception as e:
-            logger.warning("PDF generation failed (continuing with DOCX attachments): %s", e)
-
         # 5) Build attachments list
 
-        # Base attachments: JSON, transcript MD, transcript DOCX
+        # Always: JSON, transcript MD, transcript DOCX
         attachments = [
             md_transcript_path,
             docx_transcript_path,
             json_path,
         ]
 
-        # If summary is present, add summary MD and DOCXs
+        # If summary is present, add summary MD and DOCX
         if summary_text:
             attachments += [md_summary_path, docx_summary_path]
-            if docx_combined_path:
-                attachments.append(docx_combined_path)
-
-        # Add PDFs based on mode:
-        # - Always: TRANSCRIPT.pdf
-        # - If summary: SUMMARY.pdf and COMBINED.pdf
-        if pdf_files.get("transcript_pdf"):
-            attachments.append(pdf_files["transcript_pdf"])
-        if pdf_files.get("summary_pdf"):
-            attachments.append(pdf_files["summary_pdf"])
-        if pdf_files.get("combined_pdf"):
-            attachments.append(pdf_files["combined_pdf"])
 
         # 6) Send success email
         send_success_email(